longformer-one-step / config.json
Theoreticallyhugo's picture
Training in progress, epoch 1
4789048
raw
history blame
1.22 kB
{
"_name_or_path": "allenai/longformer-base-4096",
"architectures": [
"LongformerForTokenClassification"
],
"attention_mode": "longformer",
"attention_probs_dropout_prob": 0.1,
"attention_window": [
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512
],
"bos_token_id": 0,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "B-MajorClaim",
"2": "I-MajorClaim",
"3": "B-Claim",
"4": "I-Claim",
"5": "B-Premise",
"6": "I-Premise"
},
"ignore_attention_mask": false,
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-Claim": 3,
"B-MajorClaim": 1,
"B-Premise": 5,
"I-Claim": 4,
"I-MajorClaim": 2,
"I-Premise": 6,
"O": 0
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 4098,
"model_type": "longformer",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"onnx_export": false,
"pad_token_id": 1,
"sep_token_id": 2,
"torch_dtype": "float32",
"transformers_version": "4.33.0",
"type_vocab_size": 1,
"vocab_size": 50265
}